R Notebook

df <- read.csv("merged-new-version2.csv", header =TRUE, sep=",")
#df <- df[!complete.cases(df), ]  
df

df <- read.csv("merged-variety.csv", header =TRUE, sep=",")
#df <- df[!complete.cases(df), ]  
df

df <- read.csv("merged-added-functions.csv", header =TRUE, sep=",")
#df <- df[!complete.cases(df), ]  
df

df <- read.csv("merged-sim-best.csv", header =TRUE, sep=",")
#df <- df[!complete.cases(df), ]  
df

df$ln_novelty <- log(df$novelty+1)
df$ln_total <- log(df$total+1) 
df$ln_exploration <- log(df$exploration+1) 
df$group = factor(df$group)
df$ln_len_unique <- log(df$len_unique+1) 
df$ln_added_sum <- log(df$added_sum+1)
df$ln_sim_best <- log(df$sim.to.best+1)
df

df_new <- df[, sapply(df, is.numeric)]
cor(df_new, use = "complete.obs", method = "spearman" )

                                 X   Unnamed..0        phase     novelty abs_perform_diff_best      Q7_Q7_1       Q7_Q7_2      Q8_Q8_1          Q10       count       total user.requirement     infovis
X                      1.000000000  1.000000000  0.242356186 -0.04000008          -0.039079868  0.005237315 -0.0498264942 -0.040010136  0.072013496 -0.04861136 -0.09056363      -0.09731331 -0.07128520
Unnamed..0             1.000000000  1.000000000  0.242356186 -0.04000008          -0.039079868  0.005237315 -0.0498264942 -0.040010136  0.072013496 -0.04861136 -0.09056363      -0.09731331 -0.07128520
phase                  0.242356186  0.242356186  1.000000000  0.11757506          -0.092602001 -0.008916463 -0.0074969129 -0.008881488 -0.009800966 -0.13745197  0.20488584       0.16832454  0.19912172
novelty               -0.040000085 -0.040000085  0.117575064  1.00000000          -0.261877799  0.070537895  0.1749363000  0.159572432  0.090598097  0.31528952  0.35310977       0.25497735  0.24719465
abs_perform_diff_best -0.039079868 -0.039079868 -0.092602001 -0.26187780           1.000000000  0.075157400 -0.1433537188 -0.132036172 -0.239114006 -0.39974589 -0.72737264      -0.58658125 -0.61780046
Q7_Q7_1                0.005237315  0.005237315 -0.008916463  0.07053789           0.075157400  1.000000000  0.5993053799  0.228181513  0.169440714 -0.04113355 -0.09257700      -0.12024975 -0.04544927
Q7_Q7_2               -0.049826494 -0.049826494 -0.007496913  0.17493630          -0.143353719  0.599305380  1.0000000000  0.304176579  0.253625610  0.02255924  0.12261038       0.05494034  0.13418964
Q8_Q8_1               -0.040010136 -0.040010136 -0.008881488  0.15957243          -0.132036172  0.228181513  0.3041765787  1.000000000  0.299848563  0.03262785  0.13638701       0.11647285  0.11014010
Q10                    0.072013496  0.072013496 -0.009800966  0.09059810          -0.239114006  0.169440714  0.2536256098  0.299848563  1.000000000  0.11488257  0.21702201       0.17391984  0.17408292
count                 -0.048611362 -0.048611362 -0.137451974  0.31528952          -0.399745885 -0.041133553  0.0225592434  0.032627854  0.114882572  1.00000000  0.45783201       0.32531875  0.37053388
total                 -0.090563629 -0.090563629  0.204885844  0.35310977          -0.727372643 -0.092576997  0.1226103822  0.136387012  0.217022015  0.45783201  1.00000000       0.82479921  0.82990134
user.requirement      -0.097313308 -0.097313308  0.168324538  0.25497735          -0.586581246 -0.120249752  0.0549403441  0.116472851  0.173919837  0.32531875  0.82479921       1.00000000  0.78240812
infovis               -0.071285195 -0.071285195  0.199121719  0.24719465          -0.617800457 -0.045449265  0.1341896399  0.110140096  0.174082916  0.37053388  0.82990134       0.78240812  1.00000000
novelty_score          0.019692993  0.019692993  0.163234040  0.25847647          -0.603222132 -0.109564379  0.0933017185  0.116987509  0.169785938  0.37929023  0.83439087       0.52965641  0.55558433
exploration           -0.136761136 -0.136761136 -0.242448405  0.29353889          -0.165601842 -0.047418598 -0.0258093480 -0.049361187  0.001496788  0.62586084  0.33055456       0.21402281  0.22567784
Group                 -0.968129145 -0.968129145  0.000000000  0.13234300           0.002406986 -0.003551689  0.0602397593  0.048981570 -0.070924503  0.03675437  0.16405944       0.15641934  0.13672105
len_unique            -0.083893425 -0.083893425  0.188120655  0.53772703          -0.534026862  0.057679060  0.1239927882  0.253341795  0.234669806  0.43754571  0.66331157       0.45947912  0.52314195
added_sum             -0.106697125 -0.106697125 -0.143686890  0.36485491          -0.284894816 -0.013155276  0.0100795268  0.050159869  0.097675586  0.66373813  0.44949580       0.30497294  0.31672078
sim.to.best           -0.081539257 -0.081539257 -0.247582068  0.08055287          -0.332089485 -0.077542723 -0.0007748152 -0.088902334 -0.008770066  0.25114015  0.30757319       0.22293568  0.28889292
ln_novelty            -0.040000085 -0.040000085  0.117575064  1.00000000          -0.261877799  0.070537895  0.1749363000  0.159572432  0.090598097  0.31528952  0.35310977       0.25497735  0.24719465
ln_total              -0.090563629 -0.090563629  0.204885844  0.35310977          -0.727372643 -0.092576997  0.1226103822  0.136387012  0.217022015  0.45783201  1.00000000       0.82479921  0.82990134
ln_exploration        -0.136761136 -0.136761136 -0.242448405  0.29353889          -0.165601842 -0.047418598 -0.0258093480 -0.049361187  0.001496788  0.62586084  0.33055456       0.21402281  0.22567784
ln_len_unique         -0.083893425 -0.083893425  0.188120655  0.53772703          -0.534026862  0.057679060  0.1239927882  0.253341795  0.234669806  0.43754571  0.66331157       0.45947912  0.52314195
ln_added_sum          -0.106697125 -0.106697125 -0.143686890  0.36485491          -0.284894816 -0.013155276  0.0100795268  0.050159869  0.097675586  0.66373813  0.44949580       0.30497294  0.31672078
ln_sim_best           -0.081539257 -0.081539257 -0.247582068  0.08055287          -0.332089485 -0.077542723 -0.0007748152 -0.088902334 -0.008770066  0.25114015  0.30757319       0.22293568  0.28889292
                      novelty_score  exploration        Group  len_unique   added_sum   sim.to.best  ln_novelty    ln_total ln_exploration ln_len_unique ln_added_sum   ln_sim_best
X                        0.01969299 -0.136761136 -0.968129145 -0.08389343 -0.10669712 -0.0815392574 -0.04000008 -0.09056363   -0.136761136   -0.08389343  -0.10669712 -0.0815392574
Unnamed..0               0.01969299 -0.136761136 -0.968129145 -0.08389343 -0.10669712 -0.0815392574 -0.04000008 -0.09056363   -0.136761136   -0.08389343  -0.10669712 -0.0815392574
phase                    0.16323404 -0.242448405  0.000000000  0.18812066 -0.14368689 -0.2475820684  0.11757506  0.20488584   -0.242448405    0.18812066  -0.14368689 -0.2475820684
novelty                  0.25847647  0.293538891  0.132342998  0.53772703  0.36485491  0.0805528689  1.00000000  0.35310977    0.293538891    0.53772703   0.36485491  0.0805528689
abs_perform_diff_best   -0.60322213 -0.165601842  0.002406986 -0.53402686 -0.28489482 -0.3320894854 -0.26187780 -0.72737264   -0.165601842   -0.53402686  -0.28489482 -0.3320894854
Q7_Q7_1                 -0.10956438 -0.047418598 -0.003551689  0.05767906 -0.01315528 -0.0775427227  0.07053789 -0.09257700   -0.047418598    0.05767906  -0.01315528 -0.0775427227
Q7_Q7_2                  0.09330172 -0.025809348  0.060239759  0.12399279  0.01007953 -0.0007748152  0.17493630  0.12261038   -0.025809348    0.12399279   0.01007953 -0.0007748152
Q8_Q8_1                  0.11698751 -0.049361187  0.048981570  0.25334180  0.05015987 -0.0889023336  0.15957243  0.13638701   -0.049361187    0.25334180   0.05015987 -0.0889023336
Q10                      0.16978594  0.001496788 -0.070924503  0.23466981  0.09767559 -0.0087700658  0.09059810  0.21702201    0.001496788    0.23466981   0.09767559 -0.0087700658
count                    0.37929023  0.625860839  0.036754373  0.43754571  0.66373813  0.2511401493  0.31528952  0.45783201    0.625860839    0.43754571   0.66373813  0.2511401493
total                    0.83439087  0.330554560  0.164059440  0.66331157  0.44949580  0.3075731914  0.35310977  1.00000000    0.330554560    0.66331157   0.44949580  0.3075731914
user.requirement         0.52965641  0.214022810  0.156419343  0.45947912  0.30497294  0.2229356796  0.25497735  0.82479921    0.214022810    0.45947912   0.30497294  0.2229356796
infovis                  0.55558433  0.225677837  0.136721048  0.52314195  0.31672078  0.2888929166  0.24719465  0.82990134    0.225677837    0.52314195   0.31672078  0.2888929166
novelty_score            1.00000000  0.257635574  0.034698153  0.52536621  0.36970115  0.1953208213  0.25847647  0.83439087    0.257635574    0.52536621   0.36970115  0.1953208213
exploration              0.25763557  1.000000000  0.100359811  0.32609569  0.89458659  0.2914102146  0.29353889  0.33055456    1.000000000    0.32609569   0.89458659  0.2914102146
Group                    0.03469815  0.100359811  1.000000000  0.16517282  0.09810871  0.0306239632  0.13234300  0.16405944    0.100359811    0.16517282   0.09810871  0.0306239632
len_unique               0.52536621  0.326095688  0.165172821  1.00000000  0.53400908  0.2220856022  0.53772703  0.66331157    0.326095688    1.00000000   0.53400908  0.2220856022
added_sum                0.36970115  0.894586586  0.098108711  0.53400908  1.00000000  0.2664020253  0.36485491  0.44949580    0.894586586    0.53400908   1.00000000  0.2664020253
sim.to.best              0.19532082  0.291410215  0.030623963  0.22208560  0.26640203  1.0000000000  0.08055287  0.30757319    0.291410215    0.22208560   0.26640203  1.0000000000
ln_novelty               0.25847647  0.293538891  0.132342998  0.53772703  0.36485491  0.0805528689  1.00000000  0.35310977    0.293538891    0.53772703   0.36485491  0.0805528689
ln_total                 0.83439087  0.330554560  0.164059440  0.66331157  0.44949580  0.3075731914  0.35310977  1.00000000    0.330554560    0.66331157   0.44949580  0.3075731914
ln_exploration           0.25763557  1.000000000  0.100359811  0.32609569  0.89458659  0.2914102146  0.29353889  0.33055456    1.000000000    0.32609569   0.89458659  0.2914102146
ln_len_unique            0.52536621  0.326095688  0.165172821  1.00000000  0.53400908  0.2220856022  0.53772703  0.66331157    0.326095688    1.00000000   0.53400908  0.2220856022
ln_added_sum             0.36970115  0.894586586  0.098108711  0.53400908  1.00000000  0.2664020253  0.36485491  0.44949580    0.894586586    0.53400908   1.00000000  0.2664020253
ln_sim_best              0.19532082  0.291410215  0.030623963  0.22208560  0.26640203  1.0000000000  0.08055287  0.30757319    0.291410215    0.22208560   0.26640203  1.0000000000

library(car)

Loading required package: carData

mod <- lm(ln_total~ ln_novelty + ln_len_unique, data=df)
vif(mod)

   ln_novelty ln_len_unique 
      1.54079       1.54079 

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_added_sum ~ factor(group), data=df)
summary(mod)

Call:
lm(formula = ln_added_sum ~ factor(group), data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-2.0925 -1.7199 -0.4125  1.3091  6.7556 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)      2.0925     0.1588  13.175  < 2e-16 ***
factor(group)0  -0.6884     0.2231  -3.085  0.00213 ** 
factor(group)1  -0.3726     0.2204  -1.691  0.09133 .  
factor(group)2  -0.3643     0.2191  -1.663  0.09678 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.932 on 620 degrees of freedom
  (12 observations deleted due to missingness)
Multiple R-squared:  0.01515,   Adjusted R-squared:  0.01038 
F-statistic: 3.178 on 3 and 620 DF,  p-value: 0.02365

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_exploration ~ factor(group), data=df)
summary(mod)

Call:
lm(formula = ln_exploration ~ factor(group), data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.2373 -0.1828 -0.1553  0.1956  0.5269 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)     0.23727    0.01951  12.162  < 2e-16 ***
factor(group)0 -0.07103    0.02723  -2.608  0.00932 ** 
factor(group)1 -0.04822    0.02691  -1.792  0.07363 .  
factor(group)2 -0.05444    0.02676  -2.035  0.04231 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2373 on 632 degrees of freedom
Multiple R-squared:  0.01171,   Adjusted R-squared:  0.007015 
F-statistic: 2.495 on 3 and 632 DF,  p-value: 0.05892

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_len_unique ~ factor(group), data=df)
summary(mod)

Call:
lm(formula = ln_len_unique ~ factor(group), data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.1090 -1.0190  0.1159  1.0643  5.0335 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)      4.1090     0.1570  26.176  < 2e-16 ***
factor(group)0  -1.1892     0.2205  -5.392 9.89e-08 ***
factor(group)1  -0.3145     0.2178  -1.444    0.149    
factor(group)2  -0.3315     0.2165  -1.531    0.126    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.91 on 620 degrees of freedom
  (12 observations deleted due to missingness)
Multiple R-squared:  0.04969,   Adjusted R-squared:  0.04509 
F-statistic: 10.81 on 3 and 620 DF,  p-value: 6.276e-07

tapply(df$ln_len_unique, df$group, summary)

$`3`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   3.135   4.007   4.109   4.691   8.514 

$`0`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  0.000   1.207   3.497   2.920   4.205   7.953       4 

$`1`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  0.000   2.303   3.961   3.794   4.997   8.415       4 

$`2`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  0.000   2.996   3.761   3.778   4.569   8.489       4 

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_total ~ factor(group), data=df)
summary(mod)

Call:
lm(formula = ln_total ~ factor(group), data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.7373 -0.2143  0.3493  0.8471  1.7667 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)      5.1441     0.1181  43.541  < 2e-16 ***
factor(group)0  -1.0417     0.1649  -6.316 5.05e-10 ***
factor(group)1  -0.4069     0.1630  -2.497 0.012787 *  
factor(group)2  -0.5990     0.1620  -3.697 0.000237 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.437 on 632 degrees of freedom
Multiple R-squared:  0.06155,   Adjusted R-squared:  0.0571 
F-statistic: 13.82 on 3 and 632 DF,  p-value: 9.76e-09

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_sim_best ~ factor(group), data=df)
summary(mod)

Call:
lm(formula = ln_sim_best ~ factor(group), data = df)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.08356 -0.04310 -0.01492  0.02836  0.56217 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)     0.065334   0.005936  11.007  < 2e-16 ***
factor(group)0  0.018227   0.008338   2.186  0.02919 *  
factor(group)1 -0.015704   0.008231  -1.908  0.05689 .  
factor(group)2 -0.022506   0.008182  -2.751  0.00612 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.07123 on 604 degrees of freedom
  (28 observations deleted due to missingness)
Multiple R-squared:  0.04672,   Adjusted R-squared:  0.04199 
F-statistic: 9.868 on 3 and 604 DF,  p-value: 2.323e-06

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_novelty ~ factor(group), data=df)
summary(mod)

Call:
lm(formula = ln_novelty ~ factor(group), data = df)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.52892 -0.14068  0.06865  0.15783  0.28954 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)     0.52892    0.01773  29.837  < 2e-16 ***
factor(group)0 -0.13269    0.02475  -5.362 1.16e-07 ***
factor(group)1 -0.12367    0.02445  -5.058 5.56e-07 ***
factor(group)2 -0.05178    0.02431  -2.130   0.0336 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2157 on 632 degrees of freedom
Multiple R-squared:  0.05844,   Adjusted R-squared:  0.05397 
F-statistic: 13.08 on 3 and 632 DF,  p-value: 2.706e-08

df$group <- relevel(df$group, ref = "3")
mod2 <- lm(ln_exploration ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod2)

Call:
lm(formula = ln_exploration ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + 
    Q8_Q8_1 + Q10 + count, data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.7378 -0.1510 -0.1039  0.1547  0.5713 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)     0.268693   0.037650   7.137 2.72e-12 ***
factor(group)0 -0.058405   0.025897  -2.255   0.0245 *  
factor(group)1 -0.040384   0.025573  -1.579   0.1148    
factor(group)2 -0.049046   0.025214  -1.945   0.0522 .  
Q7_Q7_1        -0.003074   0.007446  -0.413   0.6798    
Q7_Q7_2         0.001945   0.007574   0.257   0.7974    
Q8_Q8_1        -0.015157   0.007835  -1.935   0.0535 .  
Q10            -0.014314   0.011506  -1.244   0.2139    
count           0.029778   0.003028   9.834  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2212 on 611 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.1499,    Adjusted R-squared:  0.1388 
F-statistic: 13.47 on 8 and 611 DF,  p-value: < 2.2e-16

df$group <- relevel(df$group, ref = "3")
mod3 <- lm(ln_exploration ~  Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod3)

Call:
lm(formula = ln_exploration ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + 
    count, data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.7572 -0.1521 -0.1140  0.1628  0.5513 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept)  0.225542   0.033282   6.777 2.89e-11 ***
Q7_Q7_1     -0.002899   0.007408  -0.391   0.6957    
Q7_Q7_2      0.001989   0.007525   0.264   0.7916    
Q8_Q8_1     -0.013677   0.007823  -1.748   0.0809 .  
Q10         -0.015032   0.011307  -1.329   0.1842    
count        0.030096   0.003031   9.929  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2218 on 614 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.1416,    Adjusted R-squared:  0.1346 
F-statistic: 20.26 on 5 and 614 DF,  p-value: < 2.2e-16

anova(mod2, mod3)

Analysis of Variance Table

Model 1: ln_exploration ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + 
    Q10 + count
Model 2: ln_exploration ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count
  Res.Df    RSS Df Sum of Sq      F Pr(>F)
1    611 29.907                           
2    614 30.200 -3  -0.29315 1.9964 0.1133

df$group <- relevel(df$group, ref = "3")
mod <- lm(ln_novelty ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod)

Call:
lm(formula = ln_novelty ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + 
    Q8_Q8_1 + Q10 + count, data = df)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.73108 -0.10789  0.05269  0.14730  0.30517 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)     0.412100   0.035171  11.717  < 2e-16 ***
factor(group)0 -0.113961   0.024192  -4.711 3.06e-06 ***
factor(group)1 -0.116408   0.023889  -4.873 1.40e-06 ***
factor(group)2 -0.051286   0.023555  -2.177  0.02984 *  
Q7_Q7_1        -0.020611   0.006956  -2.963  0.00316 ** 
Q7_Q7_2         0.028904   0.007075   4.085 4.99e-05 ***
Q8_Q8_1         0.008860   0.007319   1.210  0.22656    
Q10             0.007122   0.010748   0.663  0.50783    
count           0.013293   0.002829   4.699 3.23e-06 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2067 on 611 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.1234,    Adjusted R-squared:  0.112 
F-statistic: 10.75 on 8 and 611 DF,  p-value: 3.249e-14

df$group <- relevel(df$group, ref = "3")
mod1 <- lm(ln_novelty ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod1)

Call:
lm(formula = ln_novelty ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + 
    Q8_Q8_1 + Q10 + count, data = df)

Residuals:
     Min       1Q   Median       3Q      Max 
-0.73108 -0.10789  0.05269  0.14730  0.30517 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)     0.412100   0.035171  11.717  < 2e-16 ***
factor(group)0 -0.113961   0.024192  -4.711 3.06e-06 ***
factor(group)1 -0.116408   0.023889  -4.873 1.40e-06 ***
factor(group)2 -0.051286   0.023555  -2.177  0.02984 *  
Q7_Q7_1        -0.020611   0.006956  -2.963  0.00316 ** 
Q7_Q7_2         0.028904   0.007075   4.085 4.99e-05 ***
Q8_Q8_1         0.008860   0.007319   1.210  0.22656    
Q10             0.007122   0.010748   0.663  0.50783    
count           0.013293   0.002829   4.699 3.23e-06 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2067 on 611 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.1234,    Adjusted R-squared:  0.112 
F-statistic: 10.75 on 8 and 611 DF,  p-value: 3.249e-14

df$group <- relevel(df$group, ref = "3")
mod4 <- lm(ln_novelty ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod4)

Call:
lm(formula = ln_novelty ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + 
    count, data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.7883 -0.0854  0.0699  0.1531  0.3014 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept)  0.343113   0.031746  10.808  < 2e-16 ***
Q7_Q7_1     -0.023135   0.007066  -3.274  0.00112 ** 
Q7_Q7_2      0.032111   0.007178   4.474 9.17e-06 ***
Q8_Q8_1      0.011171   0.007462   1.497  0.13490    
Q10         -0.001228   0.010785  -0.114  0.90939    
count        0.013646   0.002891   4.720 2.93e-06 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.2115 on 614 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.07716,   Adjusted R-squared:  0.06964 
F-statistic: 10.27 on 5 and 614 DF,  p-value: 1.82e-09

anova(mod1, mod4)

Analysis of Variance Table

Model 1: ln_novelty ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + 
    count
Model 2: ln_novelty ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count
  Res.Df    RSS Df Sum of Sq      F    Pr(>F)    
1    611 26.099                                  
2    614 27.477 -3   -1.3777 10.751 6.815e-07 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

library(lmerTest)

Loading required package: lme4
Loading required package: Matrix

Attaching package: ‘lmerTest’

The following object is masked from ‘package:lme4’:

    lmer

The following object is masked from ‘package:stats’:

    step

fit.lmer <- lmer(ln_novelty ~ factor(group) + ( 1 | phase), data = df, REML= FALSE)
fit.lmer

Linear mixed model fit by maximum likelihood  ['lmerModLmerTest']
Formula: ln_novelty ~ factor(group) + (1 | phase)
   Data: df
      AIC       BIC    logLik  deviance  df.resid 
-138.4479 -111.7167   75.2239 -150.4479       630 
Random effects:
 Groups   Name        Std.Dev.
 phase    (Intercept) 0.005242
 Residual             0.214918
Number of obs: 636, groups:  phase, 4
Fixed Effects:
   (Intercept)  factor(group)0  factor(group)1  factor(group)2  
       0.52892        -0.13269        -0.12367        -0.05178  

tapply(df$ln_novelty, df$group, summary)

$`3`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 0.0000  0.4842  0.5588  0.5289  0.6162  0.6894 

$`0`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 0.0000  0.0000  0.5206  0.3962  0.6073  0.6858 

$`1`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 0.0000  0.1777  0.5062  0.4053  0.6182  0.6931 

$`2`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 0.0000  0.3871  0.5465  0.4771  0.6084  0.6904 

tapply(df$ln_total, df$group, summary)

$`3`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  4.331   4.761   5.079   5.144   5.515   5.891 

$`0`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   3.991   4.830   4.102   5.337   5.869 

$`1`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   4.553   5.089   4.737   5.580   5.882 

$`2`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   4.615   4.925   4.545   5.450   5.884 

tapply(df$ln_exploration, df$group, summary)

$`3`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 0.0000  0.0000  0.1379  0.2373  0.4612  0.6931 

$`0`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
 0.0000  0.0000  0.0000  0.1662  0.3393  0.6931 

$`1`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
0.00000 0.00000 0.02545 0.18906 0.40035 0.69315 

$`2`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
0.00000 0.00000 0.06417 0.18283 0.35241 0.69315 

tapply(df$ln_len_unique, df$group, summary)

$`3`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   3.135   4.007   4.109   4.691   8.514 

$`0`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  0.000   1.207   3.497   2.920   4.205   7.953       4 

$`1`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  0.000   2.303   3.961   3.794   4.997   8.415       4 

$`2`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
  0.000   2.996   3.761   3.778   4.569   8.489       4 

tapply(df$ln_sim_best, df$group, summary)

$`3`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
0.00000 0.01062 0.05968 0.06533 0.10374 0.22040       4 

$`0`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
0.00000 0.00000 0.06578 0.08356 0.12579 0.41985       8 

$`1`
    Min.  1st Qu.   Median     Mean  3rd Qu.     Max.     NA's 
0.000000 0.002974 0.013236 0.049630 0.064522 0.611802        8 

$`2`
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
0.00000 0.01304 0.03891 0.04283 0.06685 0.14108       8 

library(vtree)

Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio
vtree version 5.6.5 -- For more information, type: vignette("vtree")

vtree(df, "group")

vtree(df, c("phase", "group"), 
   fillcolor = c( phase = "#e7d4e8", group = "#99d8c9"),
   horiz = FALSE)

df$group <- relevel(df$group, ref = "3")
mod5 <- lm(ln_total ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod5)

Call:
lm(formula = ln_total ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + 
    Q10 + count, data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.6309 -0.2310  0.3346  0.7764  1.9667 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)     4.82832    0.22926  21.060  < 2e-16 ***
factor(group)0 -0.98353    0.15769  -6.237 8.33e-10 ***
factor(group)1 -0.42360    0.15572  -2.720 0.006709 ** 
factor(group)2 -0.59841    0.15354  -3.897 0.000108 ***
Q7_Q7_1        -0.19585    0.04534  -4.319 1.83e-05 ***
Q7_Q7_2         0.19627    0.04612   4.256 2.41e-05 ***
Q8_Q8_1        -0.10504    0.04771  -2.202 0.028060 *  
Q10             0.17920    0.07006   2.558 0.010776 *  
count           0.12749    0.01844   6.914 1.19e-11 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.347 on 611 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.1768,    Adjusted R-squared:  0.166 
F-statistic:  16.4 on 8 and 611 DF,  p-value: < 2.2e-16

df$group <- relevel(df$group, ref = "3")
mod6 <- lm(ln_total ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, data=df)
summary(mod6)

Call:
lm(formula = ln_total ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count, 
    data = df)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.5737 -0.1258  0.3665  0.7666  1.7353 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  4.19765    0.20821  20.160  < 2e-16 ***
Q7_Q7_1     -0.18970    0.04634  -4.093 4.82e-05 ***
Q7_Q7_2      0.19885    0.04708   4.224 2.77e-05 ***
Q8_Q8_1     -0.07884    0.04894  -1.611   0.1077    
Q10          0.17509    0.07073   2.475   0.0136 *  
count        0.13321    0.01896   7.025 5.71e-12 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.387 on 614 degrees of freedom
  (16 observations deleted due to missingness)
Multiple R-squared:  0.1226,    Adjusted R-squared:  0.1154 
F-statistic: 17.16 on 5 and 614 DF,  p-value: 6.62e-16

anova(mod5, mod6)

Analysis of Variance Table

Model 1: ln_total ~ factor(group) + Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + 
    count
Model 2: ln_total ~ Q7_Q7_1 + Q7_Q7_2 + Q8_Q8_1 + Q10 + count
  Res.Df  RSS Df Sum of Sq      F    Pr(>F)    
1    611 1109                                  
2    614 1182 -3   -73.013 13.409 1.744e-08 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

with(df, interaction.plot(group, phase, ln_total, ylim=c(0, max(ln_total)))) # interaction plot

with(df, interaction.plot(group, phase, ln_novelty, ylim=c(0, max(ln_novelty)))) # interaction plot

with(df, interaction.plot(group, phase, ln_exploration, ylim=c(0, max(ln_exploration)))) # interaction plot

with(df, interaction.plot(group, phase, ln_novelty, ylim=c(0, max(ln_novelty)))) # interaction plot